Job Description

Volcano ModelArk is Volcengine's one-stop large model service platform and the market leader in China's LLM space — in both product breadth and customer share. The platform provides end-to-end services spanning model inference, evaluation, and fine-tuning. Ark integrates Doubao and other leading industry models, offers a rich plugin ecosystem and AI application development services, and delivers enterprise-grade AI deployment through robust security and professional algorithm support.

We are looking for talented individuals to join us for an internship in 2026. Internships at ByteDance aim to offer students industry exposure and hands-on experience. Watch your ambitions become reality as your inspiration brings infinite opportunities at ByteDance.

Internships at ByteDance aim to provide students with hands-on experience in developing fundamental skills and exploring potential career paths. A vibrant blend of social events and enriching development workshops will be available for you to explore. Here, you will utilize your knowledge in real-world scenarios while laying a strong foundation for personal and professional growth. It runs for 12 weeks.

Candidates can apply to a maximum of two positions and will be considered for jobs in the order you apply. The application limit is applicable to ByteDance and its affiliates' jobs globally. Applications will be reviewed on a rolling basis. We encourage you to apply as early as possible. Please state your availability clearly in your resume (Start date, End date).

Summer Start Dates:
- May 11th, 2026
- May 18th, 2026
- May 26th, 2026
- June 8th, 2026
- June 22nd, 2026

Responsibilities:
- Direct involvement in core product decisions and architecture discussions for the Agent Infra platform — not busywork, not a role built around decks and status updates
- Close mentorship from an AI PM with deep experience in MaaS platforms and agent frameworks
- Contribute to product feature design and documentation for the Agent Harness layer — covering core modules including Agent Loop architecture, Memory / Context lifecycle, and Self-Improving mechanisms
- Track Agent runtime infrastructure developments across leading platforms and GitHub; produce periodic structured competitive and technical teardown reports
- Help design evaluation metrics and benchmark approaches for Harness-layer features — such as context compression quality, tool routing accuracy, and agent loop reliability
- Translate real developer pain points from user interviews and community feedback into executable product specs and working demos via AI coding

annually.